Enhanced opposition-based grey wolf optimizer for global optimization and engineering design problems

Abstract

A recently developed swarm-based meta-heuristic algorithm namely Grey Wolf Optimization algorithm (GWO), which is based on the hunting and leadership behaviours of the grey wolves in nature, has shown superior performance when compared with existing meta-heuristic algorithms. However, like other approaches, the GWO has the limitation of poor exploitation ability and being stuck in local optima when solving challenging optimization problems. To overcome these limitations, a novel technique, namely “Enhanced Opposition-Based Learning” (EOBL), has been proposed and is implemented with the GWO algorithm. The EOBL technique is largely inspired by Opposition-Based Learning (OBL) and Random Opposition-Based Learning (ROBL) techniques to efficiently balance exploration and exploitation. As a result, the Enhanced Opposition-Based Grey Wolf Optimizer (EOBGWO), an innovative approach, is proposed to increase the effectiveness of the conventional GWO algorithm. To test the efficiency of the proposed EOBGWO method, it has been tested on the standard IEEECEC2005, IEEECEC2017, and IEEECEC2019 test functions, along with several real-life engineering design problems. Furthermore, to evaluate the effectiveness and stability of the proposed technique, it has been evaluated on the challenging IEEECEC2008 special session on large scale global optimization problems. The experimental outcomes and statistical measures such as the t-test and Wilcoxon rank-sum test demonstrate that the proposed EOBGWO method outperforms the other state-of-the-art algorithms in both global optimization and engineering design problems.